© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 56563
    Prev
    Next
    INDEX
    Explanations

    do not give

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    庇
    0.43
    囤
    0.43
     neemt
    0.41
    带着
    0.41
    帶著
    0.40
    乸
    0.40
    啣
    0.40
    愜
    0.39
    贰百
    0.39
     طاقت
    0.39
    POSITIVE LOGITS
     offered
    0.98
     Offered
    0.92
     offer
    0.82
     ofrec
    0.81
    を与える
    0.81
     diberikan
    0.80
     offering
    0.79
     Offer
    0.77
     ofere
    0.76
     administered
    0.75
    Activations Density 0.003%

    No Known Activations